FNN-based tensor heterogeneous integrated Internet of Vehicles missing data estimation method

A missing data, integrated car technology, applied in neural learning methods, calculations, computer parts and other directions, to increase the degree of difference and improve the accuracy

Pending Publication Date: 2020-02-07
TIANJIN UNIVERSITY OF TECHNOLOGY
View PDF12 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In recent years, academia has done a lot of research on the recovery of missing traffic data, but how to make full use of spatio-temporal traffic patterns to improve the performance of data interpolation is still the direction of efforts

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • FNN-based tensor heterogeneous integrated Internet of Vehicles missing data estimation method
  • FNN-based tensor heterogeneous integrated Internet of Vehicles missing data estimation method
  • FNN-based tensor heterogeneous integrated Internet of Vehicles missing data estimation method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0043] The method designed in this embodiment is to carry out simulation experiments on the method of the present invention with the help of MATLAB2016 development tools. This method is compared with BGCP, HTD, XalRTC, CP_WOPT methods. Under the same test environment and test parameters, the relative error, absolute error estimation accuracy and root mean square error of these five different methods are analyzed and compared. See attached figure 1 , the specific implementation process is detailed as follows:

[0044] Step 1, system model establishment:

[0045]Step 1.1. Establish a data tensor model

[0046] 1) Dataset tensor settings

[0047] Road segment L i Indicates that E is a test road network of size p, On section road L i The average speed on (t j -Δt,t j ) is V(L i , t j ), the sampling interval Δt is 10min. per link L i Create a velocity profile a i ∈ R n , such as a i =[V(L i , t 1 ),...,V(L i , t n )] T . The speed profile contains the speed ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses an FNN-based tensor heterogeneous integrated Internet of Vehicles missing data estimation method. Traffic condition information is obtained by the Internet of Vehicles througha large amount of data collected by sensors. However, low-quality problems such as data loss and abnormal data always seriously restrict the development and application of the Internet of Vehicles. According to the FNNTEL method, robust missing data reduction is carried out on a space-time multi-dimensional data set for the problems of large road network data missing and low-quality abnormity, anda new tensor decomposition data sampling strategy is adopted; a heterogeneous integration idea is introduced into traffic data reduction modeling for the first time, and a tensor decomposition heterogeneous integration model is constructed, so that the multi-dimensionality of traffic data can be reserved, and multi-mode association of a bottom layer can be extracted; and optimizing the model by using the fuzzy neural network. Compared with relatively advanced algorithms such as BGCP, HTD and XalRTC in recent years, the FNNTEL method has the advantages that the data missing reconstruction capability is improved, the data interpolation error is reduced, and the reduction precision is effectively improved.

Description

technical field [0001] The invention belongs to the field of Internet of Things and big data processing, and in particular relates to an FNN-based tensor heterogeneous integration vehicle networking missing data estimation method. Background technique [0002] With the rapid development of Internet of Vehicles (IOV) and sensor technology, a large amount of urban traffic data is continuously collected by fixed or mobile sensors in the road network such as loop detectors, microwave detectors, and floating vehicles. It is used to capture the basic status and dynamics of the traffic road network to form multi-dimensional traffic big data. However, due to the limited spatial range of fixed sensors, mobile sensors have highly unstable spatial and temporal resolutions. At the same time, the data set collection process is often accompanied by factors such as sensor failure or transmission distortion, which inevitably lead to loss of traffic data. Or the occurrence of abnormal pheno...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G06K9/62G06N3/08H04L29/08G06F30/27
CPCH04L67/12G06N3/08G06F18/214Y02T10/40
Inventor 张婷张德干张捷高瑾馨王法玉李可
Owner TIANJIN UNIVERSITY OF TECHNOLOGY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap